发表机构
ETH Zurich; Google DeepMind（苏黎世联邦理工学院; 谷歌DeepMind）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
OmniPoint提出统一框架，采用解耦射线距离表示与双向增强策略，实现跨针孔、鱼眼等相机的零样本单目度量重建，达到最先进性能。
AI 中文摘要
从单目图像恢复度量三维几何是计算机视觉的一项基本任务，然而当前方法因固定的相机模型假设和僵化的输入方案而严重碎片化。我们提出OmniPoint，一个统一框架，旨在跨多种成像传感器（包括针孔、鱼眼和等距柱状投影）泛化度量重建，同时适应不同的几何先验。为克服投影刚性，OmniPoint摒弃了传统的平面深度回归，转而采用解耦的射线与距离表示以及解耦的训练目标，明确将相机投影模型与场景结构分离。为解决替代相机训练数据严重匮乏的问题，我们引入了一种双向增强策略，在三维空间中显式桥接有标签的透视数据与无标签的全向域。此外，为无缝集成可选输入（如相机内参或稀疏深度）而不因特征分布偏移使网络失稳，我们提出了一种稳健的信息注入机制。该机制利用可学习的输入状态嵌入来解决架构歧义，并应用向量化高斯平滑来稠密化不规则测量。大量实验表明，OmniPoint在多个基准上实现了最先进的零样本性能，为统一单目三维重建确立了稳健的新标准。
英文摘要
Recovering metric 3D geometry from monocular images is a fundamental computer vision task, yet current methods remain heavily fragmented by fixed camera model assumptions and inflexible input schemes. We present OmniPoint, a unified framework designed to generalize metric reconstruction across diverse imaging sensors, including pinhole, fisheye, and equirectangular projections, while accommodating varying geometric priors. To overcome projection rigidity, OmniPoint abandons conventional planar depth regression. It instead adopts a decoupled ray and distance representation alongside a decoupled training objective, explicitly separating the camera projection model from the scene structure. To address the severe scarcity of training data for alternative cameras, we introduce a bidirectional augmentation strategy that explicitly bridges labeled perspective data and unlabeled omnidirectional domains in 3D space. Furthermore, to seamlessly integrate optional inputs like camera intrinsics or sparse depth without destabilizing the network through feature distribution shifts, we propose a robust information injection mechanism. This mechanism utilizes learnable input state embeddings to resolve architectural ambiguity and applies vectorized Gaussian smoothing to densify irregular measurements. Extensive experiments demonstrate that OmniPoint achieves state-of-the-art zero-shot performance across multiple benchmarks, establishing a robust new standard for unified monocular 3D reconstruction.
CommentsECCV 20026. Project Page: https://botaoye.github.io/omnipoint/
